LeNir.AI articles

Teaching your AI to work

2026-10-01T00:00:00.000Z

We’ve all taken the intro to AI session or workshop. It didn’t do much, and so we went back to work. In the meantime, these AI things kept changing, evolving and spreading throughout our professional lives. At some point you may think to yourself, “yeah, I took the AI training, but honestly, I’m still just scratching the surface, and AI isn’t going away. I need to really start using this thing.”

Instead of being an AI dabbler, start teaching your AI to do work! In other words, your job is to upskill your AI.

This will provoke some very real fears such as, “I don’t want to tell the AI how to do my job because then I’ll be replaced.” Or, “I don’t want AI to do the work I like doing.” This makes sense, but look closely at the work you like doing: there are almost certainly parts of that work that you don’t really like doing. AI will be doing some parts of your job in the future, but there will be many new parts that will fill up any time savings you get from AI.

Once we’ve come to terms with all this, then you need to face up to the fact that to make AI useful, you have to invest the mental energy, and time, to teach the thing about the outputs it’s supposed to be producing. We also need to get all the background knowledge and content our brains rely on to do the work we are now offloading into our AI’s brain.

Three ways I’ve learned to “teach” my AI

(a) I ask it to do something, like produce a PowerPoint from a Word document and use the same look and feel as a previous PowerPoint.

Some might think, “My head hurts trying to really fully explain the task I need done to an AI, it’s easier just to do it myself.”

That’s true, but when you do the math you’ll usually find the ROI from the time invested in teaching the AI to do a task that you now do manually even just three or four times a year is well worth it.

To help me overcome the “my head hurts explaining stuff to the AI”, I’ve developed the skill of writing stream of consciousness prompts. I just let it all out of my mind in whatever way it wants to come out. My fingers are like stenographers, transcribing my stream of thoughts into text in real time. This gives the AI lots of information to help it do whatever it is I need it to do.

Then I go carefully through the output it generates, and meticulously call out and explain every mistake. This is the work.

Through trial and error I’ve learnt that AI learns best when I call out and explain each mistake it makes without telling it what to do to correct the mistake. Giving it the correct answer seems to stifle its learning, though sometimes I have to tell it exactly what to do otherwise it just doesn’t get done.

For example, when developing my AI pipeline to generate PowerPoint presentations, it’s better to say “the paragraph on slide five of the presentation you generated is too close to the image and to me it makes slide five look all scrunched together,” which helps the AI to learn, rather than saying, “move the paragraph on slide five further away from the image,” which provides little the AI can learn from.

(b) I share with my AI an example of a perfect output for some input and tell it to learn from that example (e.g. a PowerPoint presentation that I created, and thought was really good, from a Word document describing some new initiative). I instruct my AI to learn by example and do whatever it needs to do so that in the future, when asked to do a similar task, it will apply what it learned from the example.

(c) I spend a lot of time up front when I start a new project getting as much nuanced background knowledge and information into my AI as I can. The more my AI knows the tacit knowledge, impressions, plans, and ideas that I have in my mind, the better it can assist me at work. This is the first, and critical, step I do with clients during our first session: I help them share all the tacit knowledge their AI needs to be useful for them.

Something to try

As a first step, log in to your AI and write something like this (or copy and paste this into your AI):

I read an article, and the author said if I tell you when I think you did something wrong, like edit out an important part of some document I’ve asked you to help me edit, and I take the time to properly explain why I think it is wrong, then you will learn. He also said that if I keep investing the time to point out the errors you make, then you will make fewer and fewer errors and so become more and more helpful to me. Is that correct? Is there anything I should do, or any settings that should be set so you can build out a knowledge base of what I teach you? Can you check if you are set up and configured properly so you build a memory of all the things I teach you? I really don’t want to waste my time showing you things and then have you forget them!

Jump-start your use of AI with one-to-one Coaching on AI.

Good luck with your AI journey.
Phil.

AI role play in learning and development: why it works now

2026-09-29T00:00:00.000Z

The rapid advances of AI technologies have enabled new learning and development (L&D) and organizational development (OD) applications in which a learner talks to an AI, rather than typing into a chat. This opens up new classes of learning solutions for L&D.

One of the most popular uses of voice-to-voice in L&D is for AI role play. Role play is a useful tool for L&D and current AI models are remarkably good at it when properly set up.

Where AI role play helps

The most common uses are for sales, customer service and leadership training. Key to success is to design a variety of custom role play scenarios that closely map to what the learners will face on the job. Many companies already have well-designed rubrics and scenarios for sales enablement which can be turned into AI role play. With AI role play L&D can deploy solutions which could speed up time-to-competency for a broad variety of training needs such as: new employee training, new manager training, new customer service personnel training, executive training, new sales rep training, new product training for sales reps, new nurse training, new police officer training.

With AI role play sales reps can practice pitching a new product until they know what to say and how to say it, before getting in front of a real prospect. They can practice defending value when a customer has a cheaper quote on their desk, or handling the polite rejection when working the trade show booth, reopening a stalled deal, rehearsing a check-in when a loyal account starts drifting, and more.

AI role play is equally useful for giving young financial advisors a chance to practice helping a client who is panicking about a stock market crash and wants to pull their money out, or for new bank tellers to practice responding to a customer who needs the money on the check they deposited yesterday but it has a hold on it.

In leadership training, AI role play enables new managers to practice difficult conversations in a private safe space with a simulated character. They can practice holding a project manager who blames others for a slipped deadline accountable, or practice having an employee career conversation, or delivering negative feedback productively.

Aside from AI role play, other uses for voice-first AI in L&D include AI coach systems. They can provide personalized support in between coaching sessions, or guide a learner through a reflective discussion around a goal.

Why it suddenly works

I spent fifteen years building speech recognition middleware and applications, from Bell-Northern Research to SpeechWorks and Nuance Communications. Every voice application of that era worked in steps: recognize the words, decide what to do, then play or synthesize a reply.

The first voice applications built on large language models (LLMs) relied on cascaded systems. A user talks and their speech is transcribed, sent to an LLM, and the output is run through a text-to-speech engine so the user can hear the response. Even well-built systems typically leave a second between turns, which is significantly more than the roughly 200 ms gap in a typical conversation. Also, all the additional information that humans use to communicate during a conversation such as tone, pacing, hesitation, and inflection is lost during transcription leaving the AI with only the user’s words to work with.

The new speech systems are native audio. They have been trained natively on audio, as well as text, enabling them to take user speech directly as input, and output speech directly as audio. There is no need for transcription or text-to-speech so these systems respond much more closely to how a human would, and ‘react’ both to what was said and how it was said. Native audio systems allow an AI application to manage, and perhaps sooner than we think, even facilitate, increasingly sophisticated sessions with learners.

What to watch

As AI-powered speech systems gain traction in L&D, it’s worth keeping an eye on evolving privacy laws and regulations around the use of AI. The EU bans AI systems from inferring emotions from biometric data, including voice, at work or in education, except for safety or medical reasons. Quebec’s Law 25 only allows personal information to be processed outside the province after a privacy impact assessment shows it will be adequately protected, and under a written agreement.

The voice practice system I built doesn’t infer, label or score users’ emotions from their voice. CoachingOurselves works with its clients on what Law 25 requires, and on their own IT policies for cloud-based AI apps.

Try a live native audio AI role play demo right now.

I designed and built the voice-to-voice system behind this demo. The voice practice is sold through CoachingOurselves, which builds custom voice-first learning solutions for L&D and OD, drawing on almost twenty years of peer learning design.

What AI can’t do

Though voice AI solutions are useful, they cannot build the human connection and what Henry Mintzberg calls communityship, vital for successful organizations. Dialogue, and the guided discussions in CoachingOurselves peer learning groups are a simple, scalable human approach to leadership and organizational development.